Ahhhh!!! I figured out a huge reason the wait time is so long! When I test in chatGPT, the response happens almost immediately but it's not complete. It creates the response overtime. I'm not streaming the response in my application. I'm waiting for the entire response to be generated which it seems can take over a minute for long text. Look out for version two where I'll implement streaming the text and then streaming that text to speech!
Log in or sign up for Devpost to join the conversation.